© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8165
    Prev
    Next
    INDEX
    Explanations

    strings of numbers and special characters appearing in legal or medical texts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _
    -1.20
    //
    -1.17
    {
    -1.13
     =
    -1.09
    ;
    -1.05
        
    -1.02
    \
    -1.02
    <
    -0.99
    M
    -0.99
    R
    -0.99
    POSITIVE LOGITS
    BibitemShut
    1.50
    )");
    1.41
    $.
    1.38
    ^(@)
    1.36
     $_"
    1.29
    NUMX
    1.29
    .")]
    1.28
     Efq
    1.27
    .")
    1.27
    bibfield
    1.24
    Activations Density 2.003%

    No Known Activations